Train a JEPA world model on a set of pre-collected trajectories from an environment involving an agent in two rooms.
-
Updated
Mar 12, 2026 - Python
Train a JEPA world model on a set of pre-collected trajectories from an environment involving an agent in two rooms.
A practical explainer of JEPA, Meta AI’s Joint Embedding Predictive Architecture, with diagrams and insights comparing JEPA and Transformers.
Add a description, image, and links to the joint-embedding-prediction-architecture topic page so that developers can more easily learn about it.
To associate your repository with the joint-embedding-prediction-architecture topic, visit your repo's landing page and select "manage topics."